Training in progress, step 80

README.md

@@ -16,7 +16,7 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/quirky_lats_at_mats/harmbench_adv_training/runs/32w6twts)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/quirky_lats_at_mats/harmbench_adv_training/runs/uql9vkp6)
 # llama2-7b-sft-lora
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
@@ -38,14 +38,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2e-05
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 4
 - distributed_type: multi-GPU
-- num_devices: 2
-- total_train_batch_size: 8
-- total_eval_batch_size: 16
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - training_steps: 2000

adapter_config.json

@@ -16,12 +16,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "k_proj",
+    "up_proj",
     "q_proj",
-    "v_proj",
     "down_proj",
-    "o_proj",
-    "up_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1d8ee5e122aa5ba15194f89a4f794f9c3fe72e5c3ede8c7f35cf55983cee6c
+oid sha256:5761184767b003ef68a853f1e654ae825fcecc4c67e05afe0f397b5c96640683
 size 258001832

runs/Jun05_15-18-34_702dae2383a0/events.out.tfevents.1717600740.702dae2383a0.127543.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb3e24f12cb95eb3a27ff4aa8efdc8da51b1db8f5518fb274895c4080ae686d
-size 5777
+oid sha256:9acc67a627fef09c9db4817e984690be1714d29f5e1afbf280cdea52d5e371ed
+size 6393

step_0/README.md

@@ -203,228 +203,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ### Framework versions
 
 
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
 - PEFT 0.6.1

step_0/adapter_config.json

@@ -16,12 +16,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "k_proj",
+    "up_proj",
     "q_proj",
-    "v_proj",
     "down_proj",
-    "o_proj",
-    "up_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31603f21eaa5405647e6a387a4f62bd5c1b1efa8749cebf07f75b4a7f671ea5f
-size 6200
+oid sha256:b0d652444bf2350cdb3e94cef2e9faf380e4e1e4c94136bbe6f149254b88f14d
+size 6136

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31603f21eaa5405647e6a387a4f62bd5c1b1efa8749cebf07f75b4a7f671ea5f
-size 6200
+oid sha256:b0d652444bf2350cdb3e94cef2e9faf380e4e1e4c94136bbe6f149254b88f14d
+size 6136